[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120278-en":3,"doc-seo-120278-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120278,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Advancements in Image Classification - From Machine Learning to Deep Learning - Paper Review","Image classification, a core computer-vision task, has progressed from traditional machine learning pipelines to deep learning frameworks. The paper reviews major developments and their influence on algorithm design, anchored by widely used datasets such as CIFAR-10, ImageNet, and MNIST, and examining how dataset characteristics affect evaluation. It analyzes machine-learning approaches like SVM, Random Forest, and Decision Trees, including their feature-extraction plus classification workflow and limitations on large-scale, complex problems. It then surveys CNN-based and modern deep models such as AlexNet, VGGNet, ResNet, and ViT, comparing strengths and weaknesses to support research selection and future progress.","Advancements in Image Classification: From Machine Learning to Deep Learning  \nHaoran Cheng  \nZhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University, Zhejiang, China  \nAbstract. Image classification, as an essential task within the realm of computer vision, has evolved from traditional machine learning methods to deep learning techniques. This paper systematically reviews the growth of image classification technology, beginning with the introduction of commonly used datasets such as CIFAR-10, ImageNet, and MNIST, and exploring their impact on algorithm development. Subsequently, the paper provides an in-depth analysis of image classification methods based on machine learning, including traditional algorithms such as Support Vector Machine (SVM), Random Forest, and Decision Tree. These methods achieve image classification through two stages: feature extraction and classification, but they encounter limitations when confronted with largescale datasets and complicated tasks. Convolutional Neural Networks (CNNs) have gradually replaced traditional methods in image classification due to the rise of deep learning, resulting in improved accuracy and robustness. The paper also focuses on discussing classic deep learning models such as AlexNet, VGGNet, ResNet and ViT, analyzing their strengths and weaknesses. By comparing the performance of different methods, this paper aims to provide references for researchers in the realm of image classification, promoting further development in this area.  \n1 Introduction  \nImage classification is one of the most essential yet crucial tasks in the field of computer vision, with the primary goal of accurately assigning input images to predefined categories. As a cornerstone of computer vision, image classification is not only an independent research area but also lays the foundation for visual tasks that are more complex, like object detection, image segmentation, and scene understanding. The development of image classification techniques reflects the overall progress in the field of computer vision: from the early use of manually designed features and traditional machine learning algorithms for image classification, to the advent of the deep learning era, where end-to-end learning models, represented by Convolutional Neural Networks (CNNs), achieve automatic mapping from raw image pixels to class labels. This technological revolution has not only significantly improved classification accuracy but also greatly enhanced the model's generalization capability and adaptability in complex scenarios. Especially with the support of big data and  \n[Corresponding author: haoranc.21@intl.zju.edu.cn](Corresponding author: haoranc.21@intl.zju.edu.cn)  \n© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)).  \nhigh-performance computing resources, modern image classification models are capable of handling larger and more complex datasets, demonstrating unprecedented performance levels, making image classification increasingly important in various application scenarios.  \nIn addition, image classification has permeated various aspects of lives. In medical imaging diagnostics, image classification technology can help doctors identify lesion areas, enhancing the precision and effectiveness of diagnosis [1] . In the agricultural sector, image classification technology is used for detecting plant diseases and crop monitoring, enhancing agricultural production efficiency and yield [2] .  \nThis paper aims to systematically review the machine learning and deep learning methods in the field of image classification by examining existing technologies, comparing the benefits and drawbacks of different methods, and exploring their performance in practical applications to showcase the practical value and ","cbCaij01O3aBs0CN","https://ap.wps.com/l/cbCaij01O3aBs0CN","pdf",236226,1,"English","en",105,"# Introduction\n# Commonly used datasets for image classification\n## Overview of datasets\n## CIFAR-10 dataset\n## ImageNet dataset\n## MNIST dataset\n# Image classification methods based on machine learning\n## Support Vector Machine (SVM)\n## Random Forest\n## Decision Tree\n# Image classification methods based on deep learning\n## AlexNet\n## VGGNet\n## ResNet\n## ViT\n# Comparative analysis and practical guidance","[{\"question\":\"How does the paper structure the discussion of image classification development?\",\"answer\":\"It first introduces commonly used datasets, then reviews machine-learning methods (SVM, Random Forest, Decision Trees), and finally covers deep-learning approaches (AlexNet, VGGNet, ResNet, ViT). It compares strengths and weaknesses to support model selection in practice.\"},{\"question\":\"What are the typical limitations of traditional machine-learning image classification methods discussed in the paper?\",\"answer\":\"The paper notes that feature extraction plus classification two-stage methods can face constraints when dealing with large-scale datasets and more complicated tasks.\"},{\"question\":\"Why do deep learning models—especially CNN-based models—replace traditional approaches in the paper’s narrative?\",\"answer\":\"CNNs are described as enabling end-to-end learning from pixels to class labels, improving accuracy, robustness, and generalization, especially with support from big data and high-performance computing.\"}]","Advancements in Image Classification - From Machine Learning to Deep Learning - Paper Review | PDF",1785729210,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"advancements-in-image-classification-from-machine-learning-to-deep-learning-paper-review","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/advancements-in-image-classification-from-machine-learning-to-deep-learning-paper-review/120278/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How does the paper structure the discussion of image classification development?","Question",{"text":74,"@type":75},"It first introduces commonly used datasets, then reviews machine-learning methods (SVM, Random Forest, Decision Trees), and finally covers deep-learning approaches (AlexNet, VGGNet, ResNet, ViT). It compares strengths and weaknesses to support model selection in practice.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What are the typical limitations of traditional machine-learning image classification methods discussed in the paper?",{"text":79,"@type":75},"The paper notes that feature extraction plus classification two-stage methods can face constraints when dealing with large-scale datasets and more complicated tasks.",{"name":81,"@type":72,"acceptedAnswer":82},"Why do deep learning models—especially CNN-based models—replace traditional approaches in the paper’s narrative?",{"text":83,"@type":75},"CNNs are described as enabling end-to-end learning from pixels to class labels, improving accuracy, robustness, and generalization, especially with support from big data and high-performance computing.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]